{"id":"https://openalex.org/W4226462293","doi":"https://doi.org/10.48550/arxiv.2112.14168","title":"A Survey on Gender Bias in Natural Language Processing","display_name":"A Survey on Gender Bias in Natural Language Processing","publication_year":2021,"publication_date":"2021-12-28","ids":{"openalex":"https://openalex.org/W4226462293","doi":"https://doi.org/10.48550/arxiv.2112.14168"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2112.14168","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2112.14168","pdf_url":"https://arxiv.org/pdf/2112.14168","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2112.14168","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5017964215","display_name":"Karolina Sta\u0144czak","orcid":"https://orcid.org/0000-0001-7326-9594","observed_orcids":["https://orcid.org/0000-0001-7326-9594"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Stanczak, Karolina","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5018976680","display_name":"Isabelle Augenstein","orcid":"https://orcid.org/0000-0003-1562-7909","observed_orcids":["https://orcid.org/0000-0003-1562-7909"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Augenstein, Isabelle","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":59,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10883","display_name":"Ethics and Social Impacts of AI","score":0.8051999807357788,"subfield":{"id":"https://openalex.org/subfields/3311","display_name":"Safety Research"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T10883","display_name":"Ethics and Social Impacts of AI","score":0.8051999807357788,"subfield":{"id":"https://openalex.org/subfields/3311","display_name":"Safety Research"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T13173","display_name":"Gender Studies in Language","score":0.08619999885559082,"subfield":{"id":"https://openalex.org/subfields/3318","display_name":"Gender Studies"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T12262","display_name":"Hate Speech and Cyberbullying Detection","score":0.028200000524520874,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/gender-bias","display_name":"gender bias","score":0.9980000257492065},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"natural language processing","score":0.8709999918937683},{"id":"https://openalex.org/keywords/gender-stereotypes","display_name":"gender stereotypes","score":0.7559999823570251},{"id":"https://openalex.org/keywords/gender-fluidity","display_name":"gender fluidity","score":0.6110000014305115},{"id":"https://openalex.org/keywords/gender-bias-detection","display_name":"gender bias detection","score":0.5099999904632568},{"id":"https://openalex.org/keywords/bias-mitigation","display_name":"bias mitigation","score":0.8610000014305115},{"id":"https://openalex.org/keywords/ai-ethics","display_name":"AI ethics","score":0.5870000123977661}],"concepts":[{"id":"https://openalex.org/C2983427547","wikidata":"https://www.wikidata.org/wiki/Q93200","display_name":"Gender bias","level":2,"score":0.85763019323349},{"id":"https://openalex.org/C2776502983","wikidata":"https://www.wikidata.org/wiki/Q690182","display_name":"Contrast (vision)","level":2,"score":0.5383319854736328},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5242905020713806},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.4608151316642761},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.44909343123435974},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3901204466819763},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.35395270586013794},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.345872163772583},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.34142765402793884},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.28991445899009705},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2112.14168","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2112.14168","pdf_url":"https://arxiv.org/pdf/2112.14168","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2112.14168","doi":"https://doi.org/10.48550/arxiv.2112.14168","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2112.14168","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2112.14168","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2112.14168","pdf_url":"https://arxiv.org/pdf/2112.14168","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"score":0.7578999996185303,"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities"},{"score":0.75,"id":"https://metadata.un.org/sdg/5","display_name":"Gender equality"}],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4393230906","https://openalex.org/W2951864292","https://openalex.org/W4283162604","https://openalex.org/W4412944411","https://openalex.org/W7220037454","https://openalex.org/W3191132518","https://openalex.org/W7037148025","https://openalex.org/W4387558641","https://openalex.org/W4224912576","https://openalex.org/W4287855119"],"abstract_inverted_index":{"Language":[0],"can":[1],"be":[2],"used":[3],"as":[4,19,104,198],"a":[5,29,105,132,199],"means":[6],"of":[7,31,44,58,115,134,146,163,173,182],"reproducing":[8],"and":[9,13,15,46,52,67,75,78,83,111,158,185,189],"enforcing":[10],"harmful":[11],"stereotypes":[12],"biases":[14],"has":[16,118],"been":[17,119],"analysed":[18],"such":[20],"in":[21,37,61,70,121,139,170],"numerous":[22],"research.":[23,63,203],"In":[24],"this":[25,171],"paper,":[26],"we":[27,142],"present":[28],"survey":[30,65],"304":[32],"papers":[33,135],"on":[34,72,91,136],"gender":[35,45,59,73,85,92,103,137,183],"bias":[36,60,74,93,138,157,184],"natural":[38],"language":[39],"processing.":[40],"We":[41,64,87,191],"analyse":[42],"definitions":[43,57,181],"its":[47,109],"categories":[48],"within":[49],"social":[50],"sciences":[51],"connect":[53],"them":[54],"to":[55,81],"formal":[56],"NLP":[62,140],"lexica":[66],"datasets":[68],"applied":[69],"research":[71,90,101,174],"then":[76],"compare":[77],"contrast":[79],"approaches":[80],"detecting":[82],"mitigating":[84],"bias.":[86],"find":[88,143],"that":[89,144],"suffers":[94],"from":[95],"four":[96],"core":[97],"limitations.":[98],"1)":[99],"Most":[100,114],"treats":[102],"binary":[106],"variable":[107],"neglecting":[108],"fluidity":[110],"continuity.":[112],"2)":[113],"the":[116,147],"work":[117],"conducted":[120],"monolingual":[122],"setups":[123],"for":[124,156,201],"English":[125],"or":[126],"other":[127],"high-resource":[128],"languages.":[129],"3)":[130],"Despite":[131],"myriad":[133],"methods,":[141],"most":[145],"newly":[148],"developed":[149,169],"algorithms":[150],"do":[151],"not":[152],"test":[153],"their":[154,164],"models":[155],"disregard":[159],"possible":[160],"ethical":[161],"considerations":[162],"work.":[165],"4)":[166],"Finally,":[167],"methodologies":[168],"line":[172],"are":[175],"fundamentally":[176],"flawed":[177],"covering":[178],"very":[179],"limited":[180],"lacking":[186],"evaluation":[187],"baselines":[188],"pipelines.":[190],"suggest":[192],"recommendations":[193],"towards":[194],"overcoming":[195],"these":[196],"limitations":[197],"guide":[200],"future":[202]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":8},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":25},{"year":2022,"cited_by_count":20}],"updated_date":"2026-11-03T10:50:19.383937","created_date":"2022-05-05T00:00:00"}